JP2020154864A - Information processing device, information processing method, and information processing program - Google Patents

Abstract

To provide an information processing device, an information processing method, and an information processing program for estimating optimal measures that an object should take next for achievement of a target.SOLUTION: An information processing device 100 comprises an acquisition unit 132 and an estimation unit 136. The acquisition unit 132 acquires a level of achievement of an object to a predetermined target point preliminarily set. The estimation unit 136 estimates measures to be taken next out of measures for the object on the basis of the level of achievement acquired by the acquisition unit 132.SELECTED DRAWING: Figure 3

Description

Embodiments of the present invention relate to information processing devices, information processing methods and information processing programs.

Conventionally, techniques for predicting trends and booms have been known. For example, there is known a technique for automatically classifying a user's search query and predicting a fashion or boom in the term of the query.

JP-A-2010-33559

However, with the above-mentioned prior art, it is not always possible to estimate the optimum measure that the object should take next to achieve the goal.

For example, in the above-mentioned prior art, a predetermined data group is extracted from a user's search query, and a data group (news type, boom type, deadline date type, announcement date type, season) having a characteristic pattern prepared in advance. Compared with (type such as type), it is determined whether or not it is similar to the predetermined data group, and the predetermined data group related to the search query is classified. For example, in the above-mentioned prior art, a future fashion or boom is predicted when it is similar to a past pattern data group based on a search query input by a user. For this reason, it is not always possible to estimate the optimum measure that the object should take next in order to achieve the goal by the above-mentioned conventional technique.

The information processing apparatus according to the present application has an acquisition unit that acquires the achievement level of the object up to a predetermined target point set in advance, and the following measures regarding the object based on the achievement level acquired by the acquisition unit. It is characterized by having an estimation unit that estimates the measures to be implemented in.

According to one aspect of the embodiment, it is possible to estimate the optimal measures that the object should take next to achieve the goal.

FIG. 1 is a diagram showing an example of information processing according to an embodiment. FIG. 2 is a diagram showing a configuration example of an information processing system according to an embodiment. FIG. 3 is a diagram showing a configuration example of the information processing device according to the embodiment. FIG. 4 is a diagram showing an example of the search information storage unit according to the embodiment. FIG. 5 is a diagram showing an example of the purchase information storage unit according to the embodiment. FIG. 6 is a flowchart showing an information processing procedure according to the embodiment. FIG. 7 is a hardware configuration diagram showing an example of a computer that realizes the functions of the information processing device 100.

Hereinafter, an information processing apparatus, an information processing method, and a mode for carrying out an information processing program (hereinafter, referred to as “the embodiment”) according to the present application will be described with reference to the drawings. Note that this embodiment does not limit the information processing apparatus, information processing method, and information processing program according to the present application. Further, in the following embodiments, the same parts are designated by the same reference numerals, and duplicate description is omitted.

[1. An example of information processing]
First, an example of information processing according to the embodiment will be described with reference to FIG. FIG. 1 is a diagram showing an example of information processing according to an embodiment. The information processing according to the embodiment is performed by the information processing device 100 shown in FIG.

Prior to the description of FIG. 1, the information processing system according to the embodiment will be described with reference to FIG. FIG. 2 is a diagram showing a configuration example of the information processing system 1 according to the embodiment. As shown in FIG. 2, the information processing system 1 according to the embodiment includes a terminal device 10, a business operator device 20, an external device 30, and an information processing device 100. The terminal device 10, the operator device 20, the external device 30, and the information processing device 100 are connected to each other via a network N so as to be communicable by wire or wirelessly. The information processing system 1 shown in FIG. 2 may include a plurality of terminal devices 10, a plurality of operator devices 20, a plurality of external devices 30, and a plurality of information processing devices 100. ..

The terminal device 10 is an information processing device used by the user. The terminal device 10 is, for example, a smartphone, a tablet terminal, a notebook PC (Personal Computer), a desktop PC, a mobile phone, a PDA (Personal Digital Assistant), or the like. For example, the terminal device 10 performs various information processing in response to a user operation (for example, search or product purchase).

The business operator device 20 is an information processing device used by a business operator (for example, a talent agency) that manages an object described later. The business operator is an affiliated company related to the "business operator T" that manages the information processing apparatus 100 according to the embodiment, or a company that has some kind of contract. For example, the business operator device 20 receives information from the information processing device 100 based on the estimation result estimated by the information processing device 100.

The external device 30 is a server device that stores various behavioral information indicating user behavior (for example, search behavior, purchasing behavior, browsing behavior, etc.). For example, if the user's behavior is a search behavior, the external device 30 may be a server device that provides a predetermined search service. Further, for example, if the user's behavior is a purchasing behavior, the external device 30 may be a server device that provides a predetermined shopping service. Further, for example, if the user's behavior is a browsing behavior, the external device 30 may be a server device that provides article content or the like. The external device 30 can exist for each service as described above, for example. However, in the present embodiment, in order to simplify the explanation, it is assumed that one external device 30 has various action information because it also serves a plurality of services as described above.

Here, the premise for performing information processing according to the embodiment will be described. For example, if the object is a new talent, for the talent agency to which the new talent belongs, what direction will the new talent be sold in the future and what challenges will be taken? Is an important issue. Therefore, for example, the talent agency may set a promotion plan toward a target point according to a new talent (for example, a target point such as wanting to appear in a certain drama in the end). For example, a talent agency may set up a promotion plan that shows measures in chronological order.

However, in this promotion plan, it can be difficult to estimate how mature the new talent is, that is, how close they are to the goal and how well they are achieving the strategy. In other words, if you can accurately estimate how close you are to the target point and achieve the policy, it is appropriate for the new talent to take the next measure to bring it closer to the target point. Will be able to estimate.

Also, if you can create a successful case such as selling a new talent with the estimated policy and achieving the target point, how is the user's reaction to this successful case and the new talent at each stage in the promotion plan? By using behavioral information such as warmth, it will be possible to utilize it for studying measures for other talents.

Based on the above assumptions, the information processing apparatus 100 according to the embodiment performs information processing according to the embodiment. Specifically, the information processing apparatus 100 acquires the achievement level of the object up to a predetermined target point set in advance, and based on the acquired achievement level, among the measures related to the object, the next measure to be implemented is performed. presume. For example, the information processing apparatus 100 acquires the achievement level based on the history of the measures implemented for the object. As an example, the information processing apparatus 100 acquires the degree of achievement up to a predetermined target point in the promotion plan, which is a measure implemented for the object and is based on the policy in the promotion plan given to the object. .. Then, the information processing apparatus 100 estimates, for example, a measure for bringing the achievement level of the object closest to a predetermined target point when implemented, among the measures related to the preset object.

Further, for example, the information processing apparatus 100 acquires the achievement degree calculated based on the action information indicating a predetermined action corresponding to the object as the achievement degree. For example, the information processing apparatus 100 acquires the achievement level calculated based on the history of the measures implemented for the object and the action information indicating a predetermined action corresponding to the object. Such behavior information includes search information related to a query search using a search query (for example, the number of searches) and predetermined sales information related to an object (for example, how much was the sales of goods). Of course, the behavior information is not limited to these examples, and for example, browsing information (for example, the number of selections and the number of browsings) for the content related to the object may be further used.

Further, for example, the information processing apparatus 100 inputs the action information indicating a predetermined action corresponding to the object into the model corresponding to the target point corresponding to the object among the predetermined target points, and obtains the calculated achievement level. get. As an example, the information processing apparatus 100 uses, as a model, a model in which the relationship between the history of measures implemented for an object at a predetermined time point and the achievement level of the object at the predetermined time point is learned. Then, the achievement level of the object to be processed is acquired from the history of the measures implemented for the object to be processed. Then, the information processing apparatus 100 estimates the next measure to be implemented among the measures related to the object to be processed, based on the acquired achievement level.

Hereinafter, an example of information processing according to the embodiment will be described. Specifically, an example of information processing according to the embodiment will be described step by step with reference to FIG. In addition, a storage unit included in the information processing device 100 will be described as appropriate. In addition, regarding the point of acquiring the achievement level, it can be paraphrased that the achievement level is calculated as appropriate. Further, in the example of FIG. 1, the talent T1 is taken as an example of an object. Further, the talent T1 belongs to the office K1 which is a talent office, and the person in charge M1 of the office K1 can reach the target point set for the talent T1 in order to reach the talent T1. It is assumed that they are considering whether to take measures. Therefore, the person in charge M1 intends to use the information processing system 1 according to the embodiment. Further, in the example of FIG. 1, the achievement degree is expressed as the achievement degree score. The achievement score is an index value indicating the degree of achievement.

Here, many talents other than the talent T1 belong to the office K1. For this reason, the office K1 has actual information showing the achievements such as what kind of promotion plan was set for what kind of target point and what kind of measures were taken in the set promotion plan for each talent. It has PM1. Therefore, the person in charge M uses the operator device 20 to submit the performance information PM1 applied to the information processing device 100 and the target information G1 which is information indicating the target point set for the talent T1 ( (Transmit) (step S1). The target information G1 can be appropriately rephrased as the target point G1.

The information processing apparatus 100 generates a promotion plan for the talent T1 toward the target point G1 based on the performance information PM1 and the target information G1 received from the office K1 (step S2). Although not shown, the information processing apparatus 100 may have a storage unit (for example, a performance information storage unit) that stores performance information acquired from each business operator including the performance information PM1.

Here, the performance information PM1 will be described. The performance information PM1 is an example of the history of the measures implemented for the object, and can be said to be a promotion plan used in the past on the office K1 side. As an example, when the talent Tx1 is different from the talent T1, the performance information PM1 has been promoting by taking measures at such a stage toward the target point (final goal) such as making a drama appear. , This is information indicating that. In addition, in the performance information PM1, at a specific stage of each stage, the number of user searches for the talent Tx1 was N times, so it was decided manually that the achievement score would have been about this at this stage. Information indicating the achievement score (artificial achievement score) is also included.

Of course, the performance information PM1 includes not only the talent Tx1 but also information showing what kind of goal and what kind of promotion plan was being promoted for many other talents, and the artificial achievement score. You can do it. The information processing device 100 can generate the model shown below with higher accuracy as the amount of actual information increases.

In step S2, the information processing device 00 is a promotion plan in which, for example, a target point is set to "drama appearance" based on such performance information PM1, and in the first stage, "music CD release" and second. It is a promotion plan consisting of time-series measures such as "local sales" in the stage, "handshake event" in the third stage, "live is chair" in the fourth stage, and "concert tour" in the fifth stage. It is assumed that the plan PL1 is generated.

In the example of FIG. 1, for the sake of simplicity, an example in which the information processing device 100 generates the plan PL1 only from the actual information PM1 of the office K1 is shown, but the information processing device 100 is from another business operator. Plan PL1 may be generated in consideration of the acquired performance information. For example, the information processing apparatus 100 can generate the plan PL1 in consideration of the actual performance information acquired from a business operator (for example, another talent agency) belonging to the same category as the office K1. Further, the information processing apparatus 100 does not necessarily have to generate a promotion plan from the actual results information, and may accept submission of the promotion plan itself. In the example of FIG. 1, the information processing apparatus 100 may accept the submission of plan information indicating the promotion plan given to the talent T1 by the office K1 itself from the office K1.

Next, the information processing apparatus 100 presents the promotion plan generated in step S2 to the business operator, and receives the designation of whether or not to accept the generated promotion plan (step S3). In the example of FIG. 1, the information processing apparatus 100 presents the plan PL1 to the office K1 and receives from the office K1 whether or not to approve the plan PL1. If the office K1 is not satisfied with the plan PL1, the information processing apparatus 100 can be designated to be regenerated, or the office K1 can submit a plan generated manually, for example.

The information processing apparatus 100 shifts to the next process when consent is obtained. Specifically, the information processing apparatus 100 generates a model in which the relationship between the history of measures implemented for an object at a predetermined time point and the achievement score of the object at the predetermined time point is learned ( Step S4). Substituting with the example of FIG. 1, the information processing apparatus 100 generates a model in which the relationship between the performance information PM1 and the artificial achievement score included in the performance information PM1 is learned. Further, as described above, the achievement score is set based on the behavior information at that time (for example, search information indicating how many times the target object has been searched). Therefore, the information processing device 100 is a model in which the relationship between the action information indicating a predetermined action corresponding to the object and the artificial achievement score at the time when the action indicated by the action information occurs is learned. To generate. That is, the information processing device 100 is a model corresponding to a target point corresponding to an object, and is an object for a promotion plan in which this target point is set when action information indicating a predetermined action corresponding to the object is input. Generate a model that outputs the achievement score indicating the achievement degree of.

The information processing device 100 can use search information related to the user's search behavior for an object as behavior information. For example, the information processing apparatus 100 can use the number of searches searched using a search query for an object as search information. Further, as another example, the information processing apparatus 100 can use predetermined sales information regarding an object as action information. The target object here is an object included in the achievement information PM1, and in the above example, the talent Tx1 corresponds to the object.

For example, assuming that the model M1 is generated in step S3, the information processing device 100 stores the generated model M1 in the plan information storage unit 121. Here, the plan information storage unit 121 will be described. The plan information storage unit 121 stores a series of information regarding the promotion plan. In the example of FIG. 1, the plan information storage unit 121 has items such as "business operator ID", "plan ID", "time series", "plan details", "achievement level score", and "target model".

The "business ID" indicates identification information that identifies the business or the business device 20 of the business. The “plan ID” indicates identification information that identifies the promotion plan generated in step S2. As described above, the promotion plan according to the embodiment is composed of measures for each stage according to the time series. Therefore, "time series" indicates this time series in the promotion plan. "Plan details" is information indicating the contents of measures for each stage constituting the promotion plan.

The “achievement level score” is an achievement level score that reflects the learning result in step S4, and indicates an achievement level score set based on the generated model. In the example of the plan information storage unit 121 shown in FIG. 1, the target point of the plan PL1 which is the promotion plan identified by the business operator ID “K1” (office K1) and the plan ID “PL1” is “drama appearance”. An example is shown. In addition, Plan PL1 has "music CD release" in the first stage, "local sales" in the second stage, "handshake event" in the third stage, "live house" in the fourth stage, and "concert tour" in the fifth stage. An example of a promotion plan consisting of measures for each stage according to the time series such as ".

Therefore, the achievement score "0" associated with the first stage of the plan PL1 is the achievement score "0" when the input action information indicates a specific action content (for example, the number of searches is 10 times or less). An example in which a model M1 for calculating "0" is generated is shown. In addition, the achievement score "30" associated with the second stage of the plan PL1 is achieved when the input action information indicates a specific action content (for example, between 10 and 500 searches). An example is shown in which a model M1 is generated that calculates a degree score of less than "30". In addition, the achievement score "50" associated with the third stage of the plan PL1 is achieved when the input action information indicates a specific action content (for example, between 500 and 1000 searches). An example in which a model M1 for calculating a degree score of “30” or more and less than “50” is generated is shown. Further, the achievement score "70" associated with the fourth stage of the plan PL1 is achieved when the input action information indicates a specific action content (for example, between 1000 and 1500 searches). An example in which a model M1 for calculating a degree score of "50" or more and less than "70" is generated is shown. In addition, the achievement score "90" associated with the fifth stage of the plan PL1 is achieved when the input action information indicates a specific action content (for example, between 1500 and 2000 searches). An example in which a model M1 for calculating a degree score of "70" or more and less than "90" is generated is shown. Further, the achievement score "100" associated with the final goal (an example of the target point) of the plan PL1 is when the input action information indicates a specific action content (for example, the number of searches is 2000 or more). An example in which a model M1 for calculating an achievement score of "90" or more to "100" or less is generated is shown.

The "target model" indicates a model generated for a promotion plan identified by the corresponding "plan ID".

Further, in step S6 thereafter, the information processing apparatus 100 calculates the achievement score of the talent T1 by inputting the action information regarding the talent T1 into the model M1. Prior to this, the information processing apparatus 100 first acquires behavioral information regarding the talent T1 (step S5). For example, the information processing device 100 acquires search information, which is an example of behavioral information, from the search information storage unit 122 shown in FIG. Further, the information processing apparatus 100 acquires purchasing information, which is an example of behavior information, from the purchasing information storage unit 123 shown in FIG.

In the present embodiment, the information processing device 100 accesses the external device 30 at an arbitrary timing, acquires search information from the external device 30, and stores the acquired search information in the search information storage unit 122. The search information storage unit 122 stores search information related to the search behavior of each user. FIG. 4 is a diagram showing an example of the search information storage unit 122 according to the embodiment. In the example of FIG. 4, the search information storage unit 122 has items such as "object ID" and "search information". Further, the "search information" includes items such as "search query", "date and time", and "user ID".

The "object ID" indicates identification information that identifies the object. For example, if the object is a person, the "object ID" may be the person's name. The "search query" indicates a search query for an object identified by the corresponding "object ID". "Date and time" indicates the date and time when the search was performed in the corresponding "search query". The "user ID" indicates identification information that identifies the user who has performed the search action indicated by the corresponding "search query" and "date and time".

That is, in the example of FIG. 4, the user U51, U52, U53, etc. performed a search with the search query "Q11" regarding the target (talent T1) identified by the object ID "T1" at the date and time "DT11". Shown.

Further, in the present embodiment, the information processing device 100 accesses the external device 30 at an arbitrary timing, acquires purchase information from the external device 30, and stores the acquired purchase information in the purchase information storage unit 123. The purchase information storage unit 123 stores purchase information related to the purchase behavior of each user. FIG. 5 is a diagram showing an example of the purchase information storage unit 123 according to the embodiment. In the example of FIG. 5, the purchase information storage unit 123 has items such as “object ID” and “purchase information”. Further, the "purchase information" includes items such as "product name", "price", "date and time", and "user ID".

The "object ID" indicates identification information that identifies the object. For example, if the object is a person, the "object ID" may be the person's name. The "product name" indicates the product name of the product related to the object identified by the corresponding "object ID". "Price" indicates the price of the product. "Date and time" indicates the date and time when the product of the corresponding "product name" was purchased. The "user ID" indicates identification information that identifies a user who has purchased a product with the corresponding "product name".

That is, in the example of FIG. 5, the users U71, U72, U73, etc. purchase the product NA11 (price Y11 yen) which is a product related to the object (talent T1) identified by the object ID “T1” at the date and time “DT11”. An example is shown.

In such a state, the information processing apparatus 100 acquires the behavior information of the user regarding the talent T1 which is the behavior information corresponding to the talent T1 (step S5). That is, the information processing apparatus 100 acquires the search information associated with the object ID "T1" in the search information storage unit 122. For example, the information processing apparatus 100 extracts users who have searched so far using the search query “Q11” associated with the object ID “T1”, and counts the number of extracted users. In other words, the information processing apparatus 100 counts the number of searches for the talent T1. In such an example, it is assumed that the information processing apparatus 100 has obtained a count result of the number of searches "N11". That is, it can be said that the information processing device 100 has acquired the information indicating the number of searches "N11" regarding the talent T1 as the action information.

Further, the information processing apparatus 100 acquires the purchase information associated with the object ID "T1" in the purchase information storage unit 123. For example, the information processing apparatus 100 extracts the users who have purchased the product NA11 associated with the object ID "T1" so far, and calculates the sales of the product NA11 by counting the number of extracted users. In other words, the information processing apparatus 100 calculates the sales of the product NA11 related to the talent T1. In such an example, it is assumed that the information processing apparatus 100 has obtained a calculation result of total sales "SM11". That is, it can be said that the information processing apparatus 100 has acquired the information indicating the total sales “SM11” of the products related to the talent T1 as the action information.

Here, of course, the search information storage unit 122 and the purchase information storage unit 123 also store action information related to objects other than the talent T1. Therefore, the information processing device 100 dynamically calculates the achievement score corresponding to the performance information PM1 regarding the talent Tx1 by using the action information stored in the search information storage unit 122 or the purchase information storage unit 123, for example. You can also. For example, in the example of step S2, in the performance information PM1, at a specific stage of each stage, the number of user searches for the talent Tx1 was N times, so the achievement score would have been about this at this stage. An example is shown in which a fixed achievement score (artificial achievement score) is used. However, the information processing apparatus 100 does not use such an artificial achievement score for model generation, but uses the behavior information stored in the search information storage unit 122 and the purchase information storage unit 123 to search for the talent Tx1. Calculate the number of times and sales. Then, the information processing apparatus 100 may calculate an achievement score derived from the performance information PM1, which is an achievement score applicable to model generation, based on the calculated information.

Returning to the description of FIG. The information processing device 100 calculates the achievement score by inputting the behavior information acquired in step S5 into the corresponding model (step S6). In the example of FIG. 1, the information processing apparatus 100 inputs the search information indicating the number of searches "N11" and the purchasing information indicating the total sales "SM11" into the model M1 as the action information regarding the talent T1. Calculate the achievement score of T1. Specifically, the information processing apparatus 100 uses the model M1 to reach this target point in the plan PL1 given to the talent T1 in order to achieve the preset target point "drama appearance". The achievement score indicating the current achievement (maturity) of the talent T1 is calculated. In the example of FIG. 1, it is assumed that the information processing apparatus 100 has calculated the achievement score "45". The information processing device 100 may have a storage unit in which the calculated achievement score is stored.

Next, the information processing apparatus 100 estimates the next measure to be implemented among the measures related to the talent T1 based on the calculated achievement score (step S7). For example, the information processing device 100 estimates the next measure to be implemented by comparing the "achievement level score" in the plan information storage unit 121 with the satisfaction level score "45" calculated this time. In the example of the plan information storage unit 121 shown in FIG. 1, the achievement score “45” corresponds to the third stage. For this reason, the information processing apparatus 100 has reached the point where the third-stage policy can be implemented, or if the third-stage policy has already been implemented, the fourth stage is still available. Since we have not reached the point where we can implement the measures in the third stage, we judge that the measures in the third stage should be continued. As a result of the determination in this way, in the example of FIG. 1, the information processing apparatus 100 estimates the third-stage measure "handshake event" as the next measure to be implemented among the five-stage measures related to the talent T1.

Then, the information processing apparatus 100 provides the estimation result in step S7 to the business operator corresponding to the object (step S8). In the example of FIG. 1, the information processing apparatus 100 provides the office K1 with information indicating the third stage policy “handshake event” as an estimation result. That is, the information processing device 100 indicates that the talent T1 should hold a "handshake event" for the office K1, or if the talent T1 has already held a "handshake event", a further "handshake event" It is suggested that

By the way, as described above, the information processing apparatus 100 according to the embodiment acquires the achievement level of the object up to a predetermined target point set in advance, and based on the acquired achievement level, measures for the object. Of these, estimate the measures to be implemented next. For example, the information processing apparatus 100 uses a model learned based on the actual information of the measures implemented so far (history of the measures implemented for the object) for the acquisition (calculation) of the achievement level.

As a result, the information processing apparatus 100 according to the embodiment can estimate the optimum measure that the object should take next in order to achieve the goal.

Further, in the upper example, an example in which the object is a person (for example, a talent) is shown, but the object does not necessarily have to be a person, and may be, for example, an article (product) to be promoted. Then, the information processing device 100 according to the embodiment is promoted, for example, distribution of leaflet advertisements in the first stage, demonstration sales in the second stage, advertising activities using celebrities in the third stage, final target sales of 1 million units, and the like. Generate a plan. Then, the information processing device 100 generates a model according to the promotion plan, for example, applies the user's behavior information to the article to be promoted to the generated model, and calculates the achievement score. can do. Further, the information processing device 100 can estimate the next measure to be implemented for the article to be promoted based on the calculated satisfaction score, and provide the estimation result to the seller of the article or the store handling the article. ..

For this reason, the information processing apparatus 100 according to the embodiment can apply the information processing according to the embodiment to various objects, and therefore, for example, an attempt to enter the information processing system 1 according to the embodiment. It is possible to acquire a new business operator.

[2. Information processing device configuration]
Next, the information processing apparatus 100 according to the embodiment will be described with reference to FIG. FIG. 3 is a diagram showing a configuration example of the information processing apparatus 100 according to the embodiment. As shown in FIG. 3, the information processing device 100 includes a communication unit 110, a storage unit 120, and a control unit 130. For example, the information processing device 100 is a server device that performs information processing described with reference to FIG.

(About storage unit 120)
The storage unit 120 is realized by, for example, a semiconductor memory element such as a RAM (Random Access Memory) or a flash memory, or a storage device such as a hard disk or an optical disk. The storage unit 120 includes a plan information storage unit 121, a search information storage unit 122, and a purchase information storage unit 123. Since the plan information storage unit 121, the search information storage unit 122, and the purchase information storage unit 123 are as described in FIG. 1, detailed description thereof will be omitted here.

(About control unit 130)
The control unit 130 is realized by executing various programs stored in the storage device inside the information processing device 100 using the RAM as a work area by a CPU (Central Processing Unit), an MPU (Micro Processing Unit), or the like. .. Further, the control unit 130 is realized by, for example, an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

As shown in FIG. 4, the control unit 130 includes a reception unit 131, an acquisition unit 132, a plan generation unit 133, a model generation unit 134, a calculation unit 135, an estimation unit 136, and a provision unit 137. Then, realize or execute the information processing functions and actions described below. The internal configuration of the control unit 130 is not limited to the configuration shown in FIG. 3, and may be another configuration as long as it is a configuration for performing information processing described later. Further, the connection relationship of each processing unit included in the control unit 130 is not limited to the connection relationship shown in FIG. 3, and may be another connection relationship.

(About reception desk 131)
The reception unit 131 receives various information from the business operator. For example, the reception unit 131 receives a history of measures implemented for the object. As an example, the reception unit 131 has a track record of setting what kind of promotion plan for what kind of target point and what kind of measures have been taken in the set promotion plan for sales promotion of a predetermined object. Accept the performance information shown from the business operator. In addition, the reception unit 131 receives target information from the business operator, which is information indicating a target point set for the object to be promoted.

In addition, the reception unit 131 may also accept from the business operator whether or not to approve the promotion plan generated by the plan generation unit 133, which will be described later. For example, the reception unit 131 transmits the promotion plan generated by the plan generation unit 133 to the business operator device 20 of the corresponding business operator, and the business operator specifies whether or not to accept the promotion plan. Accept.

For this reason, the reception unit 131 performs the processes shown in steps S1 and S3 of FIG. Further, the reception unit 131 can store the actual result information in a predetermined storage unit (not shown). For example, the reception unit 131 can store the actual information in a storage unit having items such as "business ID", "object ID", and "actual information". In the example of FIG. 1, the reception unit 131 stores the actual information PM1 as the "actual information" corresponding to the business operator ID "K1" and the object ID "Tx1" in the storage unit.

(About acquisition unit 132)
The acquisition unit 132 acquires (calculates) the achievement level (achievement level score in the example of FIG. 1) of the object up to a predetermined target point set in advance. For example, the acquisition unit 132 acquires the achievement level based on the history of the measures implemented for the object. For example, the acquisition unit 132 acquires the degree of achievement up to a predetermined target point in the promotion plan given to the object.

Further, for example, the acquisition unit 132 acquires the achievement level calculated based on the action information indicating a predetermined action corresponding to the object. As an example, the acquisition unit 132 acquires the achievement level calculated based on the search information regarding the user's search behavior for the object as the action information. More specifically, the acquisition unit 132 acquires the achievement level calculated based on the number of searches searched by using the search query related to the object as the search information. Further, as another example, the acquisition unit 132 acquires the achievement level calculated based on the predetermined sales information regarding the object as the action information.

For example, the acquisition unit 132 can acquire the achievement level calculated by using the model. That is, the acquisition unit 132 acquires the degree of achievement calculated by inputting the action information indicating the predetermined action corresponding to the object into the model corresponding to the target point corresponding to the object among the predetermined target points. For example, the acquisition unit 132, as a model, has a history of measures implemented for the object at a predetermined time point (for example, actual information) and an achievement level of the object (for example, an artificial achievement level score) at the predetermined time point. Using the model in which the relationship between the two is learned, the achievement level of the object to be processed is acquired from the history of the measures implemented for the object to be processed.

In the example of FIG. 1, the acquisition unit 132 is the performance information PM1 received from the office K1, and in the case of the talent Tx1, the acquisition unit 132 is at such a stage toward the target point (final goal) such as making the drama appear. The achievement level calculated by using the model in which the relationship between the performance information PM1 indicating that the promotion was promoted by taking measures and the artificial achievement level score at each stage is acquired is acquired.

In addition, the acquisition unit 132 may also acquire action information indicating a predetermined action corresponding to the object. The behavior information includes search information regarding the user's search behavior for the object and predetermined sales information regarding the object. Therefore, for example, the acquisition unit 132 accesses the external device 30 at an arbitrary timing, acquires search information from the external device 30, and stores the acquired search information in the search information storage unit 122. Further, the acquisition unit 132 also acquires the search information from the search information storage unit 122 at a necessary timing and outputs the search information to the corresponding processing unit. For example, the acquisition unit 132 acquires search information from the search information storage unit 122 when a model is generated by the model generation unit 134 or when the satisfaction level is calculated by the calculation unit 135, and these processing units. Output to.

Further, for example, the acquisition unit 132 accesses the external device 30 at an arbitrary timing, acquires purchase information from the external device 30, and stores the acquired purchase information in the purchase information storage unit 123. In addition, the acquisition unit 132 also acquires purchase information from the purchase information storage unit 123 at a required timing and outputs the purchase information to the corresponding processing unit. For example, the acquisition unit 132 acquires purchase information from the purchase information storage unit 123 when the model is generated by the model generation unit 134 or when the satisfaction level is calculated by the calculation unit 135, and these processing units. Output to. For this reason, the acquisition unit 132 performs the process shown in step S5 of FIG.

(About plan generator 133)
The plan generation unit 133 generates a promotion plan for the object toward the target point based on the performance information and the target information received from the business operator. For example, the plan generation unit 133 may generate a promotion plan based on the performance information acquired from a plurality of different businesses. For example, the plan generation unit 133 can generate a promotion plan based on the performance information acquired from a plurality of businesses belonging to the same category.

For example, the plan generation unit 133 generates a promotion plan composed of measures for each stage according to the time series, and stores the generated promotion plan in the plan information storage unit 121. For this reason, the plan generation unit 133 performs the process shown in step S2 of FIG.

(About model generator 134)
The model generation unit 134 generates a model in which the relationship between the history (actual information) of the measures implemented for the object at a predetermined time point and the achievement level of the object at the predetermined time point is learned. Substituting with the example of FIG. 1, the model generation unit 134 generates a model in which the relationship between the performance information PM1 and the artificial achievement score included in the performance information PM1 is learned. Therefore, the model generation unit 134 has learned the relationship between the action information indicating a predetermined action corresponding to the object and the artificial achievement score at the time when the action indicated by the action information occurs. To generate. That is, the model generation unit 134 is a model corresponding to the target point corresponding to the object, and is an object for the promotion plan in which the target point is set when the action information indicating a predetermined action corresponding to the object is input. Generate a model that outputs the achievement score indicating the achievement degree of.

Further, the model generation unit 134 stores the model generated by learning in the plan information storage unit 121. For this reason, the model generation unit 134 performs the process shown in step S4 of FIG. In the example of FIG. 1, in order to simplify the explanation, the model generation unit 134 calculates the achievement score (artificial achievement degree) based on the performance information PM1 corresponding to the talent Tx1 and the action information related to the talent Tx1. An example in which model M1 was generated by learning based on the score) was shown.

However, the model generation unit 134 may generate a model by learning based on the achievement information of each of the plurality of objects and the achievement score (artificial achievement score) calculated based on the behavior information related to the object. .. In the example of FIG. 1, the model generation unit 134 is based on, for example, the performance information of each of the plurality of talents in the office K1 and the achievement score (artificial achievement score) calculated based on the behavior information related to the talent. Model M1 may be generated by learning.

(About calculation unit 135)
The calculation unit 135 calculates the achievement level of the object. For example, the calculation unit 135 calculates the achievement level by inputting the action information indicating a predetermined action corresponding to the object to be processed into the model generated on the model generation date 134. Such behavior information is behavior information acquired by the acquisition unit 132, and is, for example, search information, purchase information, or the like. In the example of FIG. 1, the calculation unit 135 inputs the search information indicating the number of searches "N11" and the purchasing information indicating the total sales "SM11" into the model M1 as the action information regarding the talent T1. Calculate the achievement score of. The calculation unit 135 can also calculate the number of searches and sales.

(About estimation unit 136)
The estimation unit 136 estimates the next measure to be implemented among the measures related to the object, based on the achievement level acquired by the acquisition unit 132. Specifically, the estimation unit 136 estimates, among the preset measures for the object, the measure that brings the achievement level of the object closest to the predetermined target point when implemented. For example, the estimation unit 136 estimates the next measure to be implemented among the measures related to the object, based on the promotion plan given to the object and the achievement level of the object up to a predetermined target point. For example, the estimation unit 136 estimates the next measure to be implemented among the measures related to the object to be processed, based on the achievement level acquired from 132 by the acquisition unit. For example, the estimation unit 136 estimates the next measure to be implemented among the measures related to the object, based on the achievement level calculated by using the model generated by the model generation unit 134. For example, the estimation unit 136 estimates as the next measure to be implemented, among the measures arranged in chronological order in the promotion plan given to the object, the measure according to the achievement level acquired by the acquisition unit.

For example, the estimation unit 136 estimates the next measure to be implemented by comparing the "achievement level score" in the plan information storage unit 121 with the satisfaction level score calculated by the calculation unit 135 using the model. Can be done. For example, when the achievement score “45” is calculated as in the example of FIG. 1, the estimation unit 136 sets the achievement score “45” and the “achievement score” a in the plan information storage unit 121. By comparing them, it is judged that the talent T1 has reached the point where the third stage measure can be implemented. Alternatively, the estimation unit 136 says that if the third stage measures have already been implemented, the third stage measures should be continued because they have not yet reached the point where the fourth stage measures can be implemented. to decide. Then, as a result of the determination in this way, the estimation unit 136 estimates the third-stage measure "handshake event" as the next measure to be implemented among the five-stage measures regarding the talent T1. For this reason, the estimation unit 136 performs the process shown in step S7 of FIG.

(About the provider 137)
The providing unit 137 provides the estimation result estimated by the estimation unit 136 to the business operator according to the object. In the example of FIG. 1, the providing unit 137 provides the office K1 with information indicating the "handshake event" in response to the estimation of the "handshake event", which is the third stage measure, as the next measure to be implemented. provide. For example, the estimation department 136 tells the office K1 that the talent T1 should hold a "handshake event", or if the talent T1 has already held a "handshake event", a further "handshake event" is held. Suggest that it should be done. For this reason, the providing unit 137 performs the process shown in step S8 of FIG.

[3. Processing procedure]
Next, the procedure of information processing according to the embodiment will be described with reference to FIG. FIG. 6 is a flowchart showing an information processing procedure according to the embodiment. In the example of FIG. 6, since the reception unit 131 of the information processing device has already received the actual information and the target information from the business operator, the information processing device 100 is requested by the business operator to estimate the policy. It shall be. Further, it is assumed that the information processing device 100 accesses the external device 30 to acquire the action information and stores it in the storage unit (for example, the search information storage unit 122 and the purchase information storage unit 123).

In such a state, the plan generation unit 133 generates a promotion plan for the object toward the target point based on the performance information and the target information received from the business operator (step S101).

Next, the model generation unit 134 generates a model based on the actual result information and the satisfaction level corresponding to the actual result information (step S102). For example, the model generation unit 134 generates a model in which the relationship between the history (actual information) of the measures implemented for the object at a predetermined time point and the achievement level of the object at the predetermined time point is learned. ..

Next, the acquisition unit 132 acquires the action information of the object to be processed (step S103). For example, the acquisition unit 132 acquires search information regarding the object to be processed from the search information storage unit 122. Further, the acquisition unit 132 acquires purchase information regarding the object to be processed from the purchase information storage unit 123.

Next, the calculation unit 135 applies the action information acquired by the acquisition unit 132 to the model corresponding to the object to be processed to calculate the satisfaction level (step S104). For example, the calculation unit 135 calculates the number of searches from the search information about the object to be processed, calculates the sales from the purchase information about the object to be processed, and applies these to the model corresponding to the object to be processed. Calculate satisfaction.

Next, the estimation unit 136 estimates the following measures among the measures related to the object to be processed based on the satisfaction score calculated by the calculation unit 135 (step S105). Then, the providing unit 137 provides the estimation result by the estimation unit 136 to the business operator regarding the object to be processed (step S106).

[4. Modification example]
The information processing apparatus 100 according to the above embodiment may be implemented in various different forms other than the above embodiment. Therefore, another embodiment of the information processing apparatus 100 will be described below.

[4-1. Satisfaction score calculation]
In the above embodiment, the calculation unit 135 calculates the satisfaction score by inputting the action information about the object to be processed to the model related to the object to be processed among the models generated by the model generation unit 134. An example is shown. For example, in the above embodiment, the calculation unit 135 shows an example of calculating the satisfaction score by increasing the number of searches and sales of the object to be processed.

However, the calculation unit 135 does not necessarily have to calculate the satisfaction score using the model, and may calculate the satisfaction score directly from the behavior information, for example. For example, the calculation unit 135 may calculate the number of searches for the object to be processed itself as the satisfaction score, or calculate the satisfaction score by performing a predetermined weighting on the number of searches for the object to be processed. You may. Similarly, the calculation unit 135 may calculate the sales itself related to the object to be processed as a satisfaction score, or calculate the satisfaction score by performing a predetermined weighting on the sales related to the object to be processed. May be good. Further, when both the number of searches and the sales are used, the calculation unit 135 may calculate the total satisfaction score by adding or multiplying the satisfaction scores calculated for each.

As a result, the information processing apparatus 100 according to the embodiment can expand the range of methods for calculating the satisfaction score.

[4-2. Reinforcement learning]
In the above embodiment, the model generation unit 134 has learned the relationship between the history (actual information) of the measures implemented for the object at a predetermined time point and the achievement level of the object at the predetermined time point. Is shown as an example of generating. Further, the estimation unit 136 estimates the future policy of the object to be processed based on the satisfaction calculated by using this model, and the providing unit 137 provides the estimation result to the business operator. For this reason, assuming that the business operator will carry out sales promotion activities related to the object with reference to the estimation result provided by the information processing device 100, the future policy of the object is the information processing related to the embodiment. It can be said that the result is reflected. Therefore, the model generation unit 134 may further strengthen the existing model by using the history of the policy reflecting the result of the information processing according to the embodiment as the actual result information.

As a result, the information processing apparatus 100 according to the embodiment can improve the accuracy of the model, so that the satisfaction score can be calculated more accurately. As a result, the information processing apparatus 100 can estimate a policy more suitable for the object, so that the degree of contribution to the sales promotion activity of the business owner can be increased.

[5. Hardware configuration]
Further, the information processing apparatus 100 according to the above embodiment is realized by, for example, a computer 1000 having a configuration as shown in FIG. FIG. 7 is a hardware configuration diagram showing an example of a computer 1000 that realizes the functions of the information processing device 100. The computer 1000 has a CPU 1100, a RAM 1200, a ROM 1300, an HDD 1400, a communication interface (I / F) 1500, an input / output interface (I / F) 1600, and a media interface (I / F) 1700.

The CPU 1100 operates based on a program stored in the ROM 1300 or the HDD 1400, and controls each part. The ROM 1300 stores a boot program executed by the CPU 1100 when the computer 1000 is started, a program that depends on the hardware of the computer 1000, and the like.

The HDD 1400 stores a program executed by the CPU 1100, data used by such a program, and the like. The communication interface 1500 receives data from another device via the communication network 50 and sends it to the CPU 1100, and transmits the data generated by the CPU 1100 to the other device via the communication network 50.

The CPU 1100 controls an output device such as a display or a printer, and an input device such as a keyboard or a mouse via the input / output interface 1600. The CPU 1100 acquires data from the input device via the input / output interface 1600. Further, the CPU 1100 outputs the generated data to the output device via the input / output interface 1600.

The media interface 1700 reads a program or data stored in the recording medium 1800 and provides the program or data to the CPU 1100 via the RAM 1200. The CPU 1100 loads the program from the recording medium 1800 onto the RAM 1200 via the media interface 1700, and executes the loaded program. The recording medium 1800 is, for example, an optical recording medium such as a DVD (Digital Versatile Disc) or PD (Phase change rewritable Disk), a magneto-optical recording medium such as MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory. And so on.

For example, when the computer 1000 functions as the information processing device 100 according to the embodiment, the CPU 1100 of the computer 1000 realizes the function of the control unit 130 by executing the program loaded on the RAM 1200. Further, the data in the storage unit 120 is stored in the HDD 1400. The CPU 1100 of the computer 1000 reads and executes these programs from the recording medium 1800, but as another example, these programs may be acquired from another device via the communication network 50.

[6. Others]
Further, each component of each of the illustrated devices is a functional concept, and does not necessarily have to be physically configured as shown in the figure. That is, the specific form of distribution / integration of each device is not limited to the one shown in the figure, and all or part of the device is functionally or physically distributed / physically in arbitrary units according to various loads and usage conditions. It can be integrated and configured.

The embodiments of the present application have been described in detail with reference to some drawings, but these are examples, and various modifications are made based on the knowledge of those skilled in the art, including the embodiments described in the disclosure column of the invention. It is possible to carry out the present invention in other improved forms.

Further, the above-mentioned "section, module, unit" can be read as "means" or "circuit". For example, the acquisition unit can be read as an acquisition means or an acquisition circuit.

1 Information processing system 10 Terminal equipment 20 Business equipment 30 External equipment 100 Information processing equipment 120 Storage unit 121 Plan information storage unit 122 Search information storage unit 123 Purchase information storage unit 130 Control unit 131 Reception unit 132 Acquisition unit 133 Plan generation unit 134 Model generation part 135 Calculation part 136 Estimating part 137 Providing part

Claims (14)

An acquisition unit that acquires the achievement level of an object up to a predetermined target point set in advance, and
An information processing apparatus having an estimation unit that estimates a policy to be implemented next among the measures related to the object based on the achievement level acquired by the acquisition unit. The first aspect of claim 1, wherein the estimation unit estimates, among the preset measures for the object, a measure that brings the achievement level of the object closest to the predetermined target point when implemented. Information processing equipment. The information processing device according to claim 1 or 2, wherein the acquisition unit acquires the achievement level based on the history of measures implemented for the object. The acquisition unit acquires the degree of achievement up to the predetermined target point in the promotion plan given to the object.
According to any one of claims 1 to 3, the estimation unit estimates a measure to be implemented next among the measures related to the object based on the promotion plan and the achievement level. The information processing device described. The information processing device according to any one of claims 1 to 4, wherein the acquisition unit acquires the achievement level calculated based on action information indicating a predetermined action corresponding to the object. The information processing device according to claim 5, wherein the acquisition unit acquires the achievement level calculated based on the search information regarding the user's search behavior for the object as the action information. The information processing device according to claim 6, wherein the acquisition unit acquires the achievement level calculated based on the number of searches searched by using the search query for the object as the search information. The information processing device according to any one of claims 5 to 7, wherein the acquisition unit acquires the achievement level calculated based on predetermined sales information about the object as the action information. The acquisition unit acquires the achievement level calculated by inputting action information indicating a predetermined action corresponding to the object into a model corresponding to the target point corresponding to the object among the predetermined target points. The information processing apparatus according to any one of claims 1 to 8, wherein the information processing apparatus is characterized. As the model, the acquisition unit uses a model in which the relationship between the history of measures implemented for the object at a predetermined time point and the achievement level of the object at the predetermined time point is learned, and uses the model as the processing target. From the history of the measures implemented for the object, the achievement level of the object to be processed is acquired.
The information according to claim 9, wherein the estimation unit estimates a measure to be implemented next among the measures related to the object to be processed based on the achievement level acquired by the acquisition unit. Processing equipment. Among the measures arranged in chronological order in the promotion plan given to the object, the estimation unit estimates the measure according to the achievement level acquired by the acquisition unit as the next measure to be implemented. The information processing device according to any one of claims 1 to 10. The information processing apparatus according to any one of claims 1 to 11, further comprising a providing unit that provides an estimation result estimated by the estimation unit to a business operator corresponding to the object. It is an information processing method executed by an information processing device.
The acquisition process to acquire the achievement level of the object up to the preset target point, and
An information processing method including an estimation process for estimating a measure to be implemented next among the measures related to the object based on the achievement level acquired by the acquisition process. An acquisition procedure for acquiring the achievement level of an object up to a predetermined target point set in advance, and
An information processing program characterized in that a computer executes an estimation procedure for estimating a measure to be implemented next among the measures related to the object based on the achievement level acquired by the acquisition procedure.

Images